traditional learning machine methods like artificial neural networks have the disadvantages of slow training speed, low generalization capability etc.
用传统的机器学习方法进行洪水预报建模存在泛化能力难以保障,训练速度慢等一些困难。
simulation results show feed-forward neural network has high approximation precision and good generalization capability to xor problem and nonlinear function.
experimental results on a number of selected databases demonstrate the expected improvement of generalization capability of the fpr-based expert systems.
as for high precision control of uncertain nonlinear systems based on nn, the generalization capability of nn is so important that the control precision is affected directly by it .